Intelligent Techniques for the Extraction and Integration of Heterogeneous Information

Developing intelligent tools for the integration of information extracted from multiple heterogeneous sources is a challenging issue to eeec-tively exploit the numerous sources available on-line in global information systems. In this paper, we propose intelligent, tool-supported techniques to information extraction and integration which take into account both struc-tured and semistructured data sources. An object-oriented language called ODL I 3 , derived from the standard ODMG, with an underlying Description Logics, is introduced for information extraction. ODL I 3 descriptions of the information sources are exploited rst to set a shared vocabulary for the sources. Information integration is performed in a semi-automatic way, by exploiting ODL I 3 descriptions of source schemas with a combination of Description Logics and clustering techniques. Techniques described in the paper have been implemented in the MOMIS system, based on a conventional mediator architecture.